Suresh Gawande

Researcher · ICAR-Directorate of Onion and Garlic Research (DOGR), Pune, Maharashtra · India

Suresh works on digital tools for onion and garlic crop protection, including deep-learning object detection models for field disease diagnosis deployed through mobile apps.

1 published paper

YOLO-ODD: An Improved YOLOv8s Model for Onion Foliar Disease Detection

A field-image dataset of 1,000 onion plants trained an upgraded YOLOv8 detector that spots Anthracnose, Stemphylium blight, Purple Blotch, and Twister disease at 77.3% accuracy and 123 frames per second — fast and light enough to run inside a farmer-facing smartphone app.

Agri Data SciencePlant PathologyIndiaMachine LearningComputer Vision

1 field note

Field notes8 min read

An AI Model That Spots Onion Disease 123 Times a Second

Researchers at ICAR's onion research institute in Pune trained a customized YOLOv8 detector on 1,000 field photos of diseased onion plants — and found that one architectural upgrade helped a lot, while a second, stacked on top of it, actually made things slightly worse.

By Suresh Gawande, Anusha Raj, Mukund Dawale, Sagar Wayal, Kiran Khandagale, Indira Bhangare, Susmita Banerjee, Ashwini Gajarushi, Rajbabu Velmurugan, and Maryam Shojaei BaghiniFrom the paper: YOLO-ODD: An Improved YOLOv8s Model for Onion Foliar Disease Detection →